美国Wayne State University朱冬宵教授学术报告
报告题目：Machine Learning Biomedical Big Data: from Community to Molecules
报告人：美国Wayne State University朱冬宵教授
In this talk, I will introduce an array of machine learning methods, tools and systems we have developed for analyzing biomedical big data at molecular, individual and community levels. At molecular level (e.g. RNA-Seq and Genome-Seq data), I will introduce a GUI based system, SAMMate, for isoform-level RNA quantification and assembly and applications to detection of alternative splicing in human diseases. At individual level (e.g. EMR data), I will introduce both conventional feature selection and newer deep feature learning approaches to prioritize disease risk factors as well as disease intervene and forecast. For case studies, I will discuss its applications to hypertension and cancer survival prediction. At community level (e.g. wireless senor data), I will review our smart community based system (both web-portal and AI-enabled chatbot) to monitor, intervene and early detection of chronic conditions, such as obesity and hypertension. Finally, we will point out some future directions.
Dongxiao Zhu is currently an Associate Professor at Department of Computer Science, Wayne State University. He received his Ph.D. from University of Michigan, Masters from Peking University and Bachelor from Shandong University. His current primary research interests are machine learning and data science with applications to learning from big data in health informatics, bioinformatics, natural language processing and multimedia. Dr. Zhu has published over 60 peer-reviewed publications and numerous book chapters and he served on several editorial boards of scientific journals. Dr. Zhu's research has been supported by NIH, NSF and private agencies and he has served on multiple NIH and NSF grant review panels. Dr. Zhu has advised numerous students at undergraduate, graduate and postdoctoral levels and his teaching interest lies in programming language, data structures and algorithms, machine learning and data science.